Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    quotations within text

    oai_token-act-pair · gpt-3.5-turbo

    quoted speech or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     occupant
    -0.74
     expiration
    -0.70
     stabilized
    -0.70
     rumored
    -0.66
     firewall
    -0.66
     designated
    -0.65
     trouble
    -0.65
     beneficiary
    -0.64
     yogurt
    -0.62
     inner
    -0.61
    POSITIVE LOGITS
     '[
    0.82
     Whilst
    0.79
    £
    0.78
     Firstly
    0.77
    iona
    0.77
     "[
    0.77
     "âĢ¦
    0.76
    yss
    0.76
     "...
    0.75
     "'
    0.75
    Act Density 0.061%

    No Known Activations